Classification of Medical Imaging Modalities Based on Visual and Signal Features

  • Amir Rajaei
  • Elham Dallalzadeh
  • Lalitha Rangarajan
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 222)

Abstract

In this paper, we present an approach to classify medical imaging modalities. Medical images are preprocessed in order to remove noises and enhance their content. The features based on texture, appearance and signal are extracted. The extracted features are concatenated to each other and considered for classification. KNN and SVM classifiers are applied to classify medical imaging modalities. The proposed approach is conducted on IMageCLEF2010 dataset. We achieve classification accuracy 95.39 % that presents the efficiency of our proposed approach.

Keywords

Medical imaging modalities classification Feature extraction Texture feature Appearance feature Signal feature K-nearest neighbor Support vector machine 

Notes

Acknowledgments

The authors would like to thank TM Lehmann, Department of Medical Informatics, RWTH Aachen, Germany, for making the database available for the experiments.

References

  1. 1.
    Lehman TM, Guld MO, Thies C, Fischer B, Keysers M, Kohnen D, Schubert H, Wein BB (2003) Content-based image retrieval in medical applications for picture archiving and communication systems. In: Proceeding of SPIE conference on medical imaging, vol 5033, pp 440–451Google Scholar
  2. 2.
    Mahmudur R Md, Bhattacharya P, Desai BC (2009) A unified image retrieval framework on local visual and semantic concept-based feature spaces. J Vis Commun Image Represent 20(7):450–462CrossRefGoogle Scholar
  3. 3.
    Florea FI, Rogozan A, Bensrhair A, Dacher J-N, Darmoni S (2005) Modality categorization by textual annotations interpretation in medical imaging. Med Inf Bio-inf, pp 1270–1274Google Scholar
  4. 4.
    Malik A, Zremic T (2005) Classification of medical images using energy information obtained from wavelet transform for medical image retrieval. In: Proceedings of 7th international workshop on enterprise networking and computing in healthcare industry, pp 124–129Google Scholar
  5. 5.
    Florea F, Barbu E, Rogozan A, Bensrhair A, Buzuloiu V (2006) Medical image categorization using a texture based symbolic description. In: Proceeding of international conference on image processing, pp 1489–1492Google Scholar
  6. 6.
    Han X, Chen Y (2010) ImageCLEF2010 modality classification in medical image retrieval: multiple feature fusion with normalized kernel function. In: Image CLEF2010 workshopGoogle Scholar
  7. 7.
    Kalpathy CJ, Hersha W (2007) Automatic image modality based classification and annotation to improve medical image retrieval, MEDINFO, pp 1334–1338Google Scholar
  8. 8.
    Pauly O, Mateus D, Navab N (2010) ImageCLEF2010 working notes on the modality classification subtask, cross language image retrieval workshopGoogle Scholar
  9. 9.
    Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24(7):971–987CrossRefGoogle Scholar
  10. 10.
    Fischer S, Sroubek F, Perrinet L, Redondo R, Cristo′ Bal G (2007) Self-invertible 2D log-gabor wavelets. Int J Comput Vision 75(2):231–246CrossRefGoogle Scholar
  11. 11.
    Rajakumar K, Muttan S (2010) Medical image retrieval using modified DCT. In: Procedia Computer Science, ICEBT2010, vol 2, pp 298–302Google Scholar
  12. 12.
    Weszka JS, Dyer CR, Rosenfeld A (1976) A comparative study of texture measures for terrain classification. IEEE Trans Syst, Man, Cybern, SMC(6):269–285Google Scholar
  13. 13.
    Galloway MM (1975) Texture analysis using gray level run lengths. Computer Graph Image Process 4:172–179CrossRefGoogle Scholar
  14. 14.
    Imran M, Rao A, Kumar GH (2010) Multibiometric systems: a comparative study of multi-algorithmic and multimodal approaches. Procedia Computer Science, ICEBT2010, vol 2, pp 207–212Google Scholar
  15. 15.
    Phinyomark A, Limsakul C, Phukpattaranont P (2009) A novel feature extraction for robust EMG pattern recognition. J Comput 1(1):71–80Google Scholar

Copyright information

© Springer India 2013

Authors and Affiliations

  • Amir Rajaei
    • 1
  • Elham Dallalzadeh
    • 1
  • Lalitha Rangarajan
    • 1
  1. 1.Department of Studies in Computer ScienceManasagangothri, University of MysoreMysoreIndia

Personalised recommendations